Báo cáo khoa học: "Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities" docx

... Linguistics Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities Baoxun Wang, Xiaolong Wang, Chengjie Sun, Bingquan Liu, Lin Sun School of Computer Science and Technology Harbin Institute ... huge number of QA pairs, and much noise infor- mation is involved. To make use of the QA pairs in cQA sites and online forums, one has to face the challeng...

Ngày tải lên: 30/03/2014, 21:20

... fields, subdivided into 232 sub-categories. 2 In the ASSIST project, we have been working on both improving the existing EST and developing a parallel tool for Russian - Russian Semantic Tag- ger ... by feeding texts from various sources into the RST and classifying words that remain unmatched. In addition, we will experiment with semi-automatic lexicon construction using an existing m...

Ngày tải lên: 08/03/2014, 21:20

... providing the means for defin- ing and implementing a sentence-based evaluation metric. Finally, the two components are combined into a single measure by implementing a weighted harmonic mean, for ... references, in the AM-FM framework, a semantic embedding is used for as- sessing the similarities between outputs and inputs (4) and, independently, an n-gram model is used for...

Ngày tải lên: 17/03/2014, 00:20

... projection rules for com- bining subject, verb, and object elements into sentence meanings are essentially rules for embedding nominal elements with verbs into structures like sentences. In our structure, ... functions that are useful in deductive inference rules. Analysis C is now of a form suitable for its inclusion in the cognitive structure. In that structure it gains...

Ngày tải lên: 23/03/2014, 13:20

... frame, as used in semantic role labeling. 3 Semantic Features Consider the verb prepare for which our sense in- ventory defines two senses: (1) to put together, assemble (e.g. He is going to prepare ... for extracting semantic information about a verb's arguments and apply it to Verb Sense Disambiguation (VSD). We contrast this method with two popular approaches to re...

Ngày tải lên: 23/03/2014, 17:20

... map- ping can miss some finer senses, but as we show in what follows, this problem in itself does not prevent us from attaining good performance in a practical WSD setting. 1.2 Information loss in ... the perfor- mance, with Resnik measure performing worse than the baseline. 4.3 Optimizing the voting process Several voting schemes were tried for combining classifiers. Simple majority...

Ngày tải lên: 31/03/2014, 03:20

... portions in P1 that are more informa- tive than portions in P2 (forward entailment). In such cases, the entailing (more informative) portions from P1 have to be translated and migrated to P2 in order ... our ap- proach to capture meaning equivalence and informa- tion disparity in cross-lingual texts. (b) In both settings the combination of lexical, syn- tactic and semantic featu...

Ngày tải lên: 19/02/2014, 19:20

... con- ditions in the prosody of the speech is purveyed. 4.3 Methodolgy We performed hold-out testing on a randomly se- lected subset of 10 interactions. The training set contains the remaining 33 interactions. ... show that using non-expert la- bels for training machine learning algorithms can be as effective as using a gold standard annotation. In this paper, we present a computational...

Ngày tải lên: 20/02/2014, 05:20

... contains about 600 thousand sentences in the training set and 60 thousand sentences in the test set (giving a total of about 10 million words). The versions of the corpus we use developed by using ... occur once in the training set. Approximately 5% of the tokens in the unsplit test set are OOV tokens. In comparison, the ratio for a comparably sized En- glish dataset is around 1%....

Ngày tải lên: 20/02/2014, 09:20

... the Chinese Web pages? To answer this question, in (Ling et al., 2008), we developed a novel approach for classifying the Web pages in Chinese using the training docu- ments in English. In this ... same semantic information. What we need to do is to uncover this latent semantic in- formation by finding out what is common among them. We did this in (Ling et al., 2008) by u...

Ngày tải lên: 08/03/2014, 00:20